© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2956
    Prev
    Next
    INDEX
    Explanations

    noun phrases related to the concept of "exercise" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GIPHY
    -0.79
    lliant
    -0.77
     Colman
    -0.74
    werfer
    -0.71
    )|\
    -0.71
     BPD
    -0.69
    :]:
    -0.68
    paravant
    -0.67
    duled
    -0.67
    contentLoaded
    -0.65
    POSITIVE LOGITS
     exercises
    1.69
     exercise
    1.63
     Exercise
    1.62
     Exer
    1.61
     Exercises
    1.59
     EXERCISE
    1.59
    Exercise
    1.56
    Exer
    1.48
     exercising
    1.46
    Exercises
    1.45
    Activations Density 0.038%

    No Known Activations